sync-plan

A skill that keeps a project plan file and Linear in sync. Linear is an issue-tracking service, and a cycle is a time-bounded group of work items similar to a sprint.

In plain words
What is it for?
Use it for full plan synchronisation, checking one ticket, pushing plan statuses to Linear, discovering cycle contents, or reviewing velocity and capacity.
Why use it?
It finds current and upcoming work, detects differences between the plan and Linear, and can update statuses in either direction.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/stoa-platform/stoa/sync-plan
Any agent
npx skills add stoa-platform/stoa --skill sync-plan
Clone the repo
git clone --depth 1 https://github.com/stoa-platform/stoa

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.03323
Opus 5 $0.00013 $0.01662
Sonnet 5 $0.00005 $0.00665
Haiku 4.5 $0.00003 $0.00332

Measured 2d ago against content hash 179bb47620b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/sync-plan/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan ↔ Linear Sync (Cycle-Aware)

Synchronize plan.md with Linear ticket statuses using cycle-driven discovery.

Target: $ARGUMENTS

Step 0: Determine Sync Mode

Argument Mode Description
(empty) Full sync Fetch current + next cycle, detect all drift
CAB-XXXX Single ticket Fetch one ticket, update plan.md marker
--push Push to Linear Push plan.md markers → Linear statuses
--cycles Cycle discovery Show current + next cycle summary only
--velocity Velocity report Show velocity history table + trend + capacity forecast

Step 1: Fetch Linear Cycles

Always start by discovering the active cycles:

linear.list_cycles(teamId: "<LINEAR_TEAM_ID>")

Identify:

  • Current cycle: type: "current" or dates containing today
  • Next cycle: type: "upcoming" or starts after current ends

Extract: cycle ID, name, start date, end date, scope (total issues), completed count.

Step 2: Fetch Cycle Issues

For each active cycle (current + next):

linear.list_issues(
  team: "<LINEAR_TEAM_ID>",
  cycle: "<cycle_id>",
  first: 50
)

For each issue, extract: identifier, title, status, priority (value + name), estimate (value), cycleId, completedAt.

Important: The status field is a string ("Done", "In Progress", "Todo", "Backlog", "Canceled", "Duplicate"), NOT a nested object.

Priority mapping: priority is {value: N, name: "..."} where 1=Urgent, 2=High, 3=Normal, 4=Low.

Estimate mapping: estimate is {value: N, name: "..."} where N is fibonacci points (1,2,3,5,8,13,21,34,55).

Step 3: Parse plan.md

Read plan.md and extract all CAB-XXXX references with their current markers:

Marker Meaning
- [x] Done locally
- [~] Partially done
- [ ] Not started or pending

Extract ticket IDs using pattern: CAB-\d{3,4}

Also identify which cycle section each ticket is in (e.g., "Cycle 7 — CURRENT" vs "Cycle 8 — NEXT").

Read the full file on GitHub · 337 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 337 lines · 26 tokens per session scan A 179bb47620b8

Subscribe to this mod's changes

sync-plan is a skill published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 3,323 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.